paper-with-me

Papers Object Segmentation

“Object Segmentation” 태그가 달린 논문 86편 · 필터 해제

Computer Vision-Based Early Detection of Container Loss at Sea

2026-04-27 · Vishakha Lall, Capt. Stanley S Pinto, Capt. Chu Xing Peng, Wu Kaiwen arxiv

Containerised shipping underpins global trade, yet container loss at sea remains a persistent safety, environmental, and economic challenge. Despite compliance with Cargo Securing Manuals, dynamic maritime conditions suc…

Object SegmentationObject Tracking

GenMatter: Perceiving Physical Objects with Generative Matter Models

2026-04-24 · Eric Li, Arijit Dasgupta, Yoni Friedman, Mathieu Huot 외 arxiv

Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation. Humans robustly detect and segment moving entities that constitute independently moveable …

Object SegmentationScene Understanding

Efficient Image Annotation via Semi-Supervised Object Segmentation with Label Propagation

2026-04-24 · Vitalii Tutevych, Raphael Memmesheimer, Luca Eichler, Dmytro Pavlichenko 외 arxiv

Reliable object perception is necessary for general-purpose service robots. Open-vocabulary detectors struggle to generalize beyond a few classes and fully supervised training of object detectors requires time-intensive …

Object Segmentation

Unsupervised Learning of Inter-Object Relationships via Group Homomorphism

2026-04-22 · Kyotaro Ushida, Takayuki Komatsu, Yoshiyuki Ohmura, Yasuo Kuniyoshi arxiv

While current deep learning models achieve high performance by learning statistical correlations from vast datasets,which stands in stark contrast to human learning. They lack the flexibility of humans-particularly preve…

Representation LearningObject Segmentation

NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation

2026-04-16 · Yi He, Tao Wang, Yi Jin, Congyan Lang 외 arxiv

Recent advances in 3D Gaussian Splatting (3DGS) have enabled highly efficient and photorealistic novel view synthesis. However, segmenting objects accurately in 3DGS remains challenging due to the discrete nature of Gaus…

Novel View SynthesisObject Segmentation

VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation

2026-04-15 · Yulu Gao, Bohao Zhang, Zongheng Tang, Jitong Liao 외 arxiv

Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for applications in embodied AI and remote collaboration. This task is exce…

Semantic SegmentationObject Segmentation

PASTA: Vision Transformer Patch Aggregation for Weakly Supervised Target and Anomaly Segmentation

2026-04-07 · Melanie Neubauer, Elmar Rueckert, Christian Rauch arxiv

Detecting unseen anomalies in unstructured environments presents a critical challenge for industrial and agricultural applications such as material recycling and weeding. Existing perception systems frequently fail to sa…

Object Segmentation

Identity-Aware U-Net: Fine-grained Cell Segmentation via Identity-Aware Representation Learning

2026-04-07 · Rui Xiao arxiv

Precise segmentation of objects with highly similar shapes remains a challenging problem in dense prediction, especially in scenarios with ambiguous boundaries, overlapping instances, and weak inter-instance visual diffe…

Representation LearningObject SegmentationCell SegmentationMetric Learning

Generalizable task-oriented object grasping through LLM-guided ontology and similarity-based planning

2026-03-27 · Hao Chen, Takuya Kiyokawa, Weiwei Wan, Kensuke Harada arxiv

Task-oriented grasping (TOG) is more challenging than simple object grasping because it requires precise identification of object parts and careful selection of grasping areas to ensure effective and robust manipulation.…

Object SegmentationPoint Clouds

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs

2026-03-18 · Jianrui Zhang, Yue Yang, Rohun Tripathi, Winson Han 외 arxiv

Token pruning is essential for enhancing the computational efficiency of vision-language models (VLMs), particularly for video-based tasks where temporal redundancy is prevalent. Prior approaches typically prune tokens e…

Computational EfficiencyObject SegmentationAction Recognition

FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding

2026-03-16 · Eadom Dessalene, Botao He, Michael Maynord, Yonatan Tussa 외 arxiv

We introduce FEEL (Force-Enhanced Egocentric Learning), the first large-scale dataset pairing force measurements gathered from custom piezoresistive gloves with egocentric video. Our gloves enable scalable data collectio…

Representation LearningAction UnderstandingObject Segmentation

Human-like Object Grouping in Self-supervised Vision Transformers

2026-03-14 · Hossein Adeli, Seoyoung Ahn, Andrew Luo, Mengmi Zhang 외 arxiv

Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties. However, their alignment with human object perception …

Object Segmentation

A novel Framework for Open-Vocabulary Multi-Object Recognition using CLIP

2026-03-06 · Wei Yu Chen, Ying Dai arxiv

To address the limitations of existing open-vocabulary object recognition methods, including high system complexity, substantial training costs, and limited generalization capability, this paper proposes a novel Open-Voc…

Object SegmentationObject Recognition

An Extended Topological Model For High-Contrast Optical Flow

2026-03-06 · Brad Turow, Jose A. Perea arxiv

In this paper, we identify low-dimensional models for dense core subsets in the space of $3\times 3$ high-contrast optical flow patches sampled from the Sintel dataset. In particular, we leverage the theory of approximat…

Object Segmentation

GarmentPile++: Affordance-Driven Cluttered Garments Retrieval with Vision-Language Reasoning

2026-03-04 · Mingleyang Li, Yuran Wang, Yue Chen, Tianxing Chen 외 arxiv

Garment manipulation has attracted increasing attention due to its critical role in home-assistant robotics. However, the majority of existing garment manipulation works assume an initial state consisting of only one gar…

Object Segmentation

Instruction-based Image Editing with Planning, Reasoning, and Generation

2026-02-26 · Liya Ji, Chenyang Qi, Qifeng Chen arxiv

Editing images via instruction provides a natural way to generate interactive content, but it is a big challenge due to the higher requirement of scene understanding and generation. Prior work utilizes a chain of large l…

Object SegmentationScene UnderstandingImage Editing

SPOT: Spatio-Temporal Obstacle-free Trajectory Planning for UAVs in Unknown Dynamic Environments

2026-02-01 · Astik Srivastava, Thomas J Chackenkulam, Bitla Bhanu Teja, Antony Thomas 외 arxiv

We address the problem of reactive motion planning for quadrotors operating in unknown environments with dynamic obstacles. Our approach leverages a 4-dimensional spatio-temporal planner, integrated with vision-based Saf…

Collision AvoidanceObject SegmentationTrajectory PlanningMotion Planning

Small but Mighty: Dynamic Wavelet Expert-Guided Fine-Tuning of Large-Scale Models for Optical Remote Sensing Object Segmentation

2026-01-14 · Yanguang Sun, Chao Wang, Jian Yang, Lei Luo arxiv

Accurately localizing and segmenting relevant objects from optical remote sensing images (ORSIs) is critical for advancing remote sensing applications. Existing methods are typically built upon moderate-scale pre-trained…

Object Segmentation

MOSAIC-GS: Monocular Scene Reconstruction via Advanced Initialization for Complex Dynamic Environments

2026-01-08 · Svitlana Morkva, Maximum Wilder-Smith, Michael Oechsle, Alessio Tonioni 외 arxiv

We present MOSAIC-GS, a novel, fully explicit, and computationally efficient approach for high-fidelity dynamic scene reconstruction from monocular videos using Gaussian Splatting. Monocular reconstruction is inherently …

Object SegmentationPoint Tracking

PartImageNet++ Dataset: Enhancing Visual Models with High-Quality Part Annotations

2026-01-04 · Xiao Li, Zilong Liu, Yining Liu, Zhuhong Li 외 arxiv

To address the scarcity of high-quality part annotations in existing datasets, we introduce PartImageNet++ (PIN++), a dataset that provides detailed part annotations for all categories in ImageNet-1K. With 100 annotated …

Object SegmentationObject RecognitionFew-Shot Learning
← 이전 21–40 / 86 다음 →